RESUMO
This paper conducts a Monte Carlo simulation study to evaluate the performance of multivariate matching methods that select a subset of treatment and control observations. The matching methods studied are the widely used nearest neighbor matching with propensity score calipers and the more recently proposed methods, optimal matching of an optimally chosen subset and optimal cardinality matching. The main findings are: (i) covariate balance, as measured by differences in means, variance ratios, Kolmogorov-Smirnov distances, and cross-match test statistics, is better with cardinality matching because by construction it satisfies balance requirements; (ii) for given levels of covariate balance, the matched samples are larger with cardinality matching than with the other methods; (iii) in terms of covariate distances, optimal subset matching performs best; (iv) treatment effect estimates from cardinality matching have lower root-mean-square errors, provided strong requirements for balance, specifically, fine balance, or strength-k balance, plus close mean balance. In standard practice, a matched sample is considered to be balanced if the absolute differences in means of the covariates across treatment groups are smaller than 0.1 standard deviations. However, the simulation results suggest that stronger forms of balance should be pursued in order to remove systematic biases due to observed covariates when a difference in means treatment effect estimator is used. In particular, if the true outcome model is additive, then marginal distributions should be balanced, and if the true outcome model is additive with interactions, then low-dimensional joints should be balanced. Copyright © 2016 John Wiley & Sons, Ltd.
Assuntos
Método de Monte Carlo , Pontuação de Propensão , Viés , HumanosRESUMO
Context: Somatrogon is a long-acting recombinant human growth hormone treatment developed as a once-weekly treatment for pediatric patients with growth hormone deficiency (GHD). Objective: Evaluate patient and caregiver perceptions of the treatment burden associated with the once-weekly somatrogon injection regimen vs a once-daily Somatropin injection regimen. Methods: Pediatric patients (≥3 to <18 years) with GHD receiving once-daily somatropin at enrollment were randomized 1:1 to Sequence 1 (12 weeks of once-daily Somatropin, then 12 weeks of once-weekly somatrogon) or Sequence 2 (12 weeks of once-weekly somatrogon, then 12 weeks of once-daily Somatropin). Treatment burden was assessed using validated questionnaires completed by patients and caregivers. The primary endpoint was the difference in mean overall life interference (LI) total scores after each 12-week treatment period (somatrogon vs Somatropin), as assessed by questionnaires. Results: Of 87 patients randomized to Sequence 1 (nâ =â 43) or 2 (nâ =â 44), 85 completed the study. Once-weekly somatrogon had a significantly lower treatment burden than once-daily Somatropin, based on mean overall LI total scores after somatrogon (8.63) vs Somatropin (24.13) treatment (mean difference -15.49; 2-sided 95% CI -19.71, -11.27; Pâ <â .0001). Once-weekly somatrogon was associated with greater convenience, higher satisfaction with treatment experience, and less LI. The incidence of treatment-emergent adverse events (TEAEs) for Somatropin and somatrogon was 44.2% and 54.0%, respectively. No severe or serious AEs were reported. Conclusion: In pediatric patients with GHD, once-weekly somatrogon had a lower treatment burden and was associated with a more favorable treatment experience than once-daily Somatropin.